Continuous-Time Machine Learning: A Unified Mathematical Perspective
cs.LG, cs.AI
Submitted: 2026-09-15
Updated: 2026-09-15
Code: https://github.com/itxwaleedrazzaq/ctml-review
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates
- Efficiently Modeling Long Sequences with Structured State Spaces
- Neuronal Circuit Policies
- Liquid Time-constant Recurrent Neural Networks as Universal Approximators
- ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
- OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization
- FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning
- On Neural Differential Equations
- Comprehensive Review of Neural Differential Equations for Time Series Analysis
- Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mamba
- Transformers in Time Series: A Survey
- Discrete Event, Continuous Time RNNs
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- Liquid Resistance Liquid Capacitance Networks
- LFM2 Technical Report
- Multi-Time Attention Networks for Irregularly Sampled Time Series
- Liquid Structural State-Space Models
- Hyper-Connections
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks